RIDTech: Rice Plant Disease Identification and Detection Technology through Classification of Microorganisms using Fuzzy Neural Network

These codes were used in our undergraduate study, see the abstract below:

Rice, the most stable food crop, is considered a prime product of the Philippines, serving as source of income to millions of Filipino farmers. Because of its economic importance as commodity and industry, rice plant's health critical. Disease identification and management are inherent factors and time incorporated is an indispensable element. The traditional way of culturing microorganisms in laboratories that can be used in identifying rice plant disease take a considerable amount of time, and the time consumed could instead be used to alleviate the agricultural problem. Another method is through identification of visible structures produced by the pathogens but this method is confusing and prone to error, and thus unreliable. In this study, RIDtech was developed to provide a more accurate and systematic analysis regarding the health conditions of rice plant, eliminate time consuming traditional method, and facilitate the farmers to acquire higher crop productivity. This study used sound signal processing system to efficiently detect and identify the three common microorganisms that cause diseases in the farmland of Philippines: Xanthomonas oryzae, Thanatephorus cucumeris and Magnaporthe grisea. A Graphic User Interface made in Visual Basic will allow the user to record sounds. The frequency of the microbes in the leaves of the rice plant will serve as the input of the system. Frequent movement of microbes will be collected using an electret microphone observed in an anechoic chamber. The sound recording will be processed using MATLAB software that includes recording system, sound enhancement, feature extraction, database and fuzzy neural network. The Fuzzy neural networks have features that make it well suited to this study in offering fast and accurate performance of sound signal processing. The system will base on 450 recorded sound data. Based on the result, the program will generate a report in PDF format. Overall, this study allows the prevention and early management of harmful microorganisms in rice plants. During the field test, the project was found to be fully functional and 100 percent accurate.